- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Attention Prediction Using Partial Differential on Color Spaces
摘要： Human attention prediction has attracted significant interest in recent years due to its promising contributions to various computer vision applications. In this paper, we present a simple and effective framework for extracting meaningful features from the color space. The feature extraction is based on computing the second order partial differential for the input image. The features extracted from the RGB and LUV spaces are combined to form a saliency map of natural images. Based on the public dataset used in previous works, we compare our proposed algorithm with several competitive approaches presented in the literature and the results demonstrate that the proposed method is effective. We also apply the feature based on the LUV space to improve some of the previous approaches, and our experimental results show that the application is meaningful for enhancing the accuracy of human attention prediction.
关键词： saliency map,second order partial differential,visual saliency
更新于2025-09-19 17:15:36
-
[IEEE 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) - Orlando, FL, USA (2018.12.17-2018.12.20)] 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) - GAN-Based Super Resolution for Accurate 3D Surface Reconstruction from Light Field Skin Images Towards Haptic Palpation
摘要： The development of vision technology for observation of skin surface and diagnosis of skin disease for preventing secondary infections caused by direct skin touch has consistently been in the medical field spotlight. Many studies have been conducted to acquire three dimensional (3D) data through stereo images, multiple images, and lasers because (3D) data of in-vivo skin image is essential for accurate medical diagnosis. However, stereo vision systems or 3D laser systems for obtaining 3D information require high cost and have high computational complexity, and hence they have not been used universally. Additionally, the use of such systems is still not preferred in the medical field due to limitations on visual decision making. Therefore, a haptic diagnosis system that can blend vision information from a camera and palpation information from a dermatologist has been considered. In this study, we propose a 3D skin surface reconstruction method using a light field camera for haptic rendering and palpation. To achieve this goal, we addressed the low resolution problem, which has been consistently present in light field cameras, through the generative adversarial nets (GANs)-based super resolution method, and exploited the light field system which has been applied only to the object scene for obtaining 3D skin surface texture. Experimental results show that the method proposed in this study is promising and offers sufficient potential for haptic diagnosis.
关键词： Light field images,deep learning,3D skin surface reconstruction,disparity map,haptic palpation,super resolution
更新于2025-09-19 17:15:36
-
[IEEE 2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE) - Shah Alam (2018.7.11-2018.7.12)] 2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE) - Accurate Disparity Map Estimation Based on Edge-preserving Filter
摘要： This paper proposes a new algorithm to estimate a disparity map. This map contains depth information from stereo matching process. Generally, this process is sensitive to low texture areas and high noise on images with high different brightness and contrast. To get over these problems, the proposed algorithm utilizes the RGB channels at the matching stage and edge-preserving filter at the second and final stage. The filter is known as Guided Filter (GF). The GF kernel well-recovered low texture areas which is able to reduce noise and sharpen the images. Additionally, GF is strong against the distortions due to high brightness and contrast. The propose algorithm produces accurate results on the disparity map for the low textured regions. The proposed work in this paper produces accurate results and performs much better compared to some established algorithms based on the quantitative and qualitative measurements using standard stereo benchmarking evaluation from the Middlebury.
关键词： stereo matching,sum of absolute differences,computer vision,disparity map,guided filter
更新于2025-09-19 17:15:36
-
[IEEE 2018 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM) - Bangkok, Thailand (2018.12.16-2018.12.19)] 2018 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM) - Distributed-based Hierarchical Clustering System for Large-scale Semiconductor Wafers
摘要： In this paper, we propose a Distributed-based Hierarchical Clustering System for Large-Scale Semiconductor Wafers (DHCSSW). By applying the big-data clustering algorithm, the proposed system makes it feasible to cluster large-scale wafers with up to 320,000 wafers. To verify the performance of our approach, we used simulated wafer maps. The experimental results show that our system outperformed in processing large-scale wafers, suggesting that currently used hierarchical clustering is insufficient in analyzing large-scale wafer maps. In addition, some failure patterns, which the existing approach is not able to detect, can be found with the DHCSSW. We anticipate that the DHCSSW will contribute to identifying failure patterns in semiconductor wafers.
关键词： Distributed computing system,Big data analytics,Semiconductor wafer map,Hierarchical clustering
更新于2025-09-19 17:15:36
-
Effective and Efficient Photo -Based PM2.5 Concentration Estimation
摘要： Air pollution has become a worldwide concerned issue and automatical estimation of air quality can provide a positive guidance to both individual and industrial behaviors. Given that the traditional instrument-based method requires high economic, labor costs on instrument purchase and maintenance, this paper proposes an effective, efficient, and cheap photo-based method for the air quality estimation in the case of particulate matter (PM2.5). The success of the proposed method lies in extracting two categories of features (including the gradient similarity and distribution shape of pixel values in the saturation map) by observing the photo appearances captured under different PM2.5 concentrations. Specifically, the gradient similarity is extracted to measure the structural information loss with the consideration that PM2.5 attenuates the light rays emitted from the objects and accordingly distorts the structures of the formed photo. Meanwhile, the saturation map is fit by the Weibull distribution to quantify the color information loss. By combining two features, a primary PM2.5 concentration estimator is obtained. Next, a nonlinear function is adopted to map the primary one to the real PM2.5 concentration. Sufficient experiments on real data captured by professional PM2.5 instrument demonstrate the effectiveness and efficiency of the proposed method. Specifically, it is highly consistent with real sensor’s measures and requires low implementation time.
关键词： saturation map,Air quality estimation,PM2.5 concentration,photo-based,gradient similarity
更新于2025-09-19 17:15:36
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Motion Occlusions for Automatic Generation of Relative Depth Maps
摘要： Recovering of the depth structure of a scene from monocular video content provides an important advantage in applications such as AR (placing and removing of objects) or 3D-TV and 3D cinema (2D-to-3D video conversion). In this paper, we present an automatic method to generate relative depth maps from monocular video sequences. It relies on the dynamic occlusion depth cue to recover the depth order of objects in the scene. The forward and backward motion analysis between each two consecutive frames allows the calculation of their dynamic occlusions. We estimate the motion using a modified version of the EpicFlow. Our modifications to this optical flow method made it coherent in forward-backward directions without compromising its performance. Thanks to this new feature, occlusions are simpler to calculate than the approaches used in the relevant literature. The obtained occlusions allow order deduction of the objects contained in the image. These objects are obtained using a segmentation approach which considers both color and motion. Ours results show a small improvement to the quality of the optical flow while adding the forward/backward coherence. With respect to the depth ordering our approach obtains slightly better results than the reference method while removing a computationally costly step from the processing.
关键词： depth ordering,occlusions,segmentation,relative depth map
更新于2025-09-19 17:15:36
-
An improved Logistic chaotic map and self-adaptive model for image encryption
摘要： An image encryption scheme provides the means for securely transmitting images over public channels. In this paper, I proposed an efficient permutation-diffusion image encryption scheme based on an improved Logistic chaotic map (ILCM) and self-adaptive model. The permutation phase permuted the addresses of the image pixel using the first chaotic sequence generated by ILCM, created the parameter which was related to the number of 0's in the bit-planes of the plain-image. Since this different plain-image had different parameter for permutation even just only a bit is changed in the plain-image. The diffusion phase then altered the pixel values of the permuted image with combined space-bit-plane exchange and XOR operation with the second chaotic sequence generated by ILCM. Simulations and performance evaluations showed that the ILCM with larger chaotic ranges and better chaotic behaviors compare with the Logistic chaotic map (LCM). Numerical experiments also showed that our proposed self-adaptive method can considerably enhance the cryptosystem resistance against known/chosen-plaintext and differential attacks. Theoretical analysis and computer experiments confirmed that the new algorithm was secure and reliable, with high potential to be adopted for network security and secure communications.
关键词： Chaotic encryption,improved Logistic chaotic map (ILCM),self-adaptive model,permutation-diffusion
更新于2025-09-19 17:15:36
-
Rapid design of a heliostat field by analytic geometry methods and evaluation of maximum optical efficiency map
摘要： Many procedures have been developed to design and optimize a heliostat field, however it is a rather challenging work partly because many influencing factors of a heliostat optical efficiency, especially the shading and blocking efficiency, are computationally intensive. And it's difficult to judge whether a heliostat field layout is an ideal design intuitively and reliable. In this paper, two concise and accurate analytic geometry methods (AGM-I and AGM-II) are developed to identify the heliostats with the possibilities of shadowing or blocking a given heliostat firstly. The results compared with the Sassi method and bounding sphere & Sassi method show that the same accurate results are obtained while the computational time is significantly reduced by 32% and 23%, respectively. Then an intuitive approach is proposed to optimize and evaluate the rationality of a heliostat field layout by applying the maximum optical efficiency map (MOEM). Finally, a heliostat field based on the Gemasolar plant is studied, whose optical efficiency is optimized and evaluated by the proposed methods. Compared with the un-optimized result and the result optimized by using the reference method, the MOEM optimization result of the heliostat field with higher instantaneous optical efficiency and annual optical efficiency is more reasonable.
关键词： Maximum optical efficiency map,Optical efficiency optimization,Solar power tower,Heliostat field,Analytic geometry methods
更新于2025-09-19 17:15:36
-
Dynamics and quantum yields of H <sub/>2</sub> + CH <sub/>2</sub> CO as a primary photolysis channel in CH <sub/>3</sub> CHO
摘要： The first experimental observation of the primary photochemical channel of acetaldehyde leading to the formation of ketene (CH2CO) and hydrogen (H2) molecular products is reported. Acetaldehyde (CH3CHO) was photolysed in a molecular beam at 305.6 nm and the resulting H2 product characterized using velocity-map ion (VMI) imaging. Resonance-enhanced multiphoton ionization (REMPI), via two-photon excitation to the double-well EF 1S+ g state, was used to state-selectively ionize the H2 and determine angular momentum distributions for H2 (n = 0) and H2 (n = 1). Velocity-map ion images were obtained for H2 (n = 0 and 1, J = 5), allowing the total translational energy release of the photodissociation process to be determined. Following photolysis of CH3CHO in a gas cell, the CH2CO co-fragment was identified, using Fourier transform infrared spectroscopy, by its characteristic infrared absorption at 2150 cm?1. The measured quantum yield of the CH2CO + H2 product channel at 305.0 nm is f = 0.0075 ± 0.0025 for both 15 Torr of neat CH3CHO and a mixture with 745 Torr of N2. Although small, this result has implications for the atmospheric photochemistry of carbonyls and this reaction represents a new tropospheric source of H2. Quasi-classical trajectory (QCT) simulations on a zero-point energy corrected reaction-path potential are also performed. The experimental REMPI and VMI image distributions are not consistent with the QCT simulations, indicating a non reaction-path mechanism should be considered.
关键词： FTIR,velocity-map imaging,atmospheric chemistry,hydrogen,quantum yield,REMPI,ketene,acetaldehyde,photodissociation
更新于2025-09-19 17:15:36
-
[IEEE 2019 IEEE BiCMOS and Compound semiconductor Integrated Circuits and Technology Symposium (BCICTS) - Nashville, TN, USA (2019.11.3-2019.11.6)] 2019 IEEE BiCMOS and Compound semiconductor Integrated Circuits and Technology Symposium (BCICTS) - Over 70-GHz 4.9-V <sub/>ppdiff</sub> InP linear driver for next generation coherent optical communications
摘要： We propose a multichannel random discrete fractional Fourier transform (MRFrFT) with random weighting coefficients and partial transform kernel functions. First, the weighting coefficients of each channel are randomized. Then, the kernel functions, selected based on a choice scheme, are randomized using a group of random phase-only masks (RPOMs). The proposed MRFrFT can be carried out both electronically and optically, and its main features and properties have been given. Numerical simulation about one-dimensional signal demonstrates that the MRFrFT has an important feature that the magnitude and phase of its output are both random. Moreover, the MRFrFT of two-dimensional image can be viewed as a security enhanced image encryption scheme due to the large key space and the sensitivity to the private keys.
关键词： fractional Fourier transform,image encryption,Chaotic logistic map,random phase mask
更新于2025-09-19 17:13:59